HGRU + Beam Search + Guided attention

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Speech2 results

DialogueonSwitchboard corpus
Accuracy· 2020-02-20
85
SOTA
Guiding attention in Sequence-to-sequence models for Dialogue Act prediction arXiv:2002.08801
DialogueonICSI Meeting Recorder Dialog Act (MRDA) corpus
Accuracy· 2020-02-20
91.6
best: 92.4 (Pretrained Hierarchical Transformer)
Guiding attention in Sequence-to-sequence models for Dialogue Act prediction arXiv:2002.08801